On the effect of ensemble size on the discrete and continuous ranked probability scores

被引:124
作者
Ferro, Christopher A. T. [1 ]
Richardson, David S. [2 ]
Weigel, Andreas P. [3 ]
机构
[1] Univ Exeter, Sch Engn Comp & Math, Exeter EX4 4QF, Devon, England
[2] European Ctr Medium Range Weather Forecasts, Reading RG2 9AX, Berks, England
[3] Fed Off Meteorol & Climatol MeteoSwiss, Zurich, Switzerland
基金
英国自然环境研究理事会;
关键词
Brier score; forecast verification; reliability; sharpness; skill scores;
D O I
10.1002/met.45
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
Four recent papers have investigated the effects of ensemble size on the Brier score (BS) and discrete ranked probability score (RPS) attained by ensemble-based probabilistic forecasts. The connections between these papers are described and their results are generalized. In particular, expressions, explanations and estimators for the expected effect of ensemble size on the RPS and continuous ranked probability score (CRPS) are obtained. Copyright (c) 2008 Royal Meteorological Society.
引用
收藏
页码:19 / 24
页数:6
相关论文
共 15 条
[1]  
Brier G. W., 1950, MON WEATHER REV, V78, P1, DOI [10.1175/1520-0493(1950)078%3C0001:VOFEIT%3E2.0.CO
[2]  
2, 10.1175/1520-0493(1950)0782.0.co
[3]  
2, DOI 10.1016/0016-0032(94)90228-3]
[4]  
David HA, 1998, STAT SCI, V13, P368
[5]  
Epstein E. S., 1969, Journal of Applied Meteorology (1962-1982), V8, P985
[6]   Comparing Probabilistic forecasting systems with the brier score [J].
Ferro, Christopher A. T. .
WEATHER AND FORECASTING, 2007, 22 (05) :1076-1088
[7]  
Hersbach H, 2000, WEATHER FORECAST, V15, P559, DOI 10.1175/1520-0434(2000)015<0559:DOTCRP>2.0.CO
[8]  
2
[9]  
MIJLLER WA, 2005, J CLIMATE, V18, P1513
[10]  
Murphy A. H., 1973, Journal of Applied Meteorology, V12, P595, DOI 10.1175/1520-0450(1973)012<0595:ANVPOT>2.0.CO